WO2025058222A1 - Method for structuring unstructured data using artificial intelligence - Google Patents

Abstract

A method performed by a computing device according to some embodiments of the present disclosure comprises the steps of: acquiring first text data including unstructured data extracted from a medical record database; acquiring summary information about the first text data from the first text data by inputting the first text data and a predetermined first prompt to a first summary information generation model based on artificial intelligence; and using regular expressions or a pre-trained information classification model based on artificial intelligence to acquire, from the summary information about the first text data, a dataset in which one or more pieces of text included in the summary information about the first text data are classified into predetermined categories, wherein the dataset has a structured format including columns composed of the predetermined categories and rows composed of the one or more pieces of text corresponding to the respective columns.

Description

A method for formalizing unstructured data using artificial intelligence

The present disclosure relates to a technology for processing data, and more specifically, to a method for using artificial intelligence technology to format unstructured data and store the formatted data in a database.

Currently, medical record information is diverse in terms of information types such as surgery, treatment, prescription, and questionnaire, and the same medical terms are expressed in different ways depending on the hospital or medical staff. Therefore, when conducting clinical research or retrospective research using CDW (Clinical Data Warehouse), the conversion rate of medical record information into standardized data is significantly low.

Therefore, in order to smoothly use medical record information when conducting retrospective studies, research is required to standardize medical record information, which is unstructured data.

Korean Patent Publication No. 10-2006-0062680 (published on June 12, 2006) discloses a method for converting medical data.

The present disclosure has been made in response to the aforementioned background technology, and seeks to provide a method of using artificial intelligence technology to standardize unstructured data and store the standardized data in a database.

The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

According to some embodiments of the present disclosure for solving the above-described problem, a method performed in a computing device may include: obtaining first text data including unstructured data extracted from a medical record database; obtaining summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model; and obtaining a dataset in which at least one text included in the summary information of the first text data is classified by predetermined item from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or a regular expression, wherein the dataset is formed in a structured format including columns including the predetermined items and rows including the at least one text corresponding to each column.

Alternatively, the predetermined first prompt may include a request sentence for requesting the first summary information generation model to output summary information of the first text data.

Alternatively, the first summary information generation model can be trained to generate summary information for input text data using second text data including unstructured data extracted from a medical record database, summary information of the second text data, and the predetermined first prompt.

Alternatively, the first summary information generation model may be trained to make the first output information similar to the summary information of the second text data by comparing the first output information output by inputting the second text data and the predetermined first prompt with the summary information of the second text data.

Alternatively, the summary information of the second text data may be output by the pre-trained second summary information generation model in response to inputting the second text data and the predetermined first prompt into the artificial intelligence-based pre-trained second summary information generation model.

Alternatively, the pre-trained second summary information generation model can be pre-trained to output summary information including text corresponding to the predetermined item from the third text data, using third text data including unstructured data extracted from a medical record database and the predetermined first prompt.

Alternatively, the summary information of the text data output by the second summary information generation model in response to inputting the text data and the prompt to the second summary information generation model can be used as ground truth data in the learning process of the first summary information generation model.

Alternatively, the predetermined items may include personal information including at least one of age or gender; physical condition information related to a body; and disease condition information related to a disease.

Alternatively, the pre-trained information classification model may include a natural language processing model that is pre-trained to process natural language contained in text data to classify the text into predetermined categories.

Alternatively, the step of obtaining the dataset may include the step of determining whether a pattern exists in the summary information of the first text data; and the step of obtaining the dataset by differently applying the methodology of obtaining the dataset based on whether the pattern exists.

Alternatively, the step of acquiring the dataset may include a step of acquiring the dataset in which text included in the summary information of the first text data is classified into predetermined items by using a regular expression corresponding to a pattern, if a pattern exists in the summary information of the first text data.

Alternatively, the step of obtaining the dataset may include a step of obtaining the dataset in which text included in the summary information of the first text data is classified by predetermined items using the pre-learned information classification model, if a pattern does not exist in the summary information of the first text data.

Alternatively, the method may further include: a step of comparing the at least one text classified by the at least one predetermined item with the reference information determined for each of the at least one predetermined item; a step of removing the at least one error text from the dataset if there is at least one error text among the at least one text that does not conform to the reference information determined for each of the at least one predetermined item as a result of comparing the at least one text; and a step of storing the dataset from which the at least one error text has been removed.

Alternatively, in a computing device, a processor; and a memory, wherein the processor is capable of performing the following operations: obtaining first text data including unstructured data extracted from a medical record database; obtaining summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model; and obtaining a dataset in which at least one text included in the summary information of the first text data is classified by predetermined items from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or a regular expression, wherein the dataset is formed in a structured format including columns composed of the predetermined items and rows composed of the at least one text corresponding to each column.

Alternatively, a computer program stored in a computer-readable storage medium, the computer program, when executed by a computing device, may include operations including: obtaining first text data including unstructured data extracted from a medical record database; obtaining summary information of the first text data from the first text data by inputting the first text data and a first predetermined prompt into an artificial intelligence-based first summary information generation model; and obtaining a dataset in which at least one text included in the summary information of the first text data is classified by predetermined items from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or a regular expression, the dataset being in a structured format including columns including the predetermined items and rows including the at least one text corresponding to each column.

The present disclosure can reduce the burden of work required for conversion or interpretation by medical staff, thereby providing faster and more accurate results to patients.

The present disclosure can increase the accuracy of diagnosis and data reliability by reducing human errors or inconsistencies that may occur during data entry and conversion processes.

The present disclosure can contribute to improving medical quality by enabling smooth information sharing among various medical institutions and medical professionals by standardizing medical records.

The present disclosure can reduce computing resources generated from unstructured data, and the technology for converting big data can be expected to have a cost-saving effect on medical research and artificial intelligence-based research.

The effects obtainable from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by a person skilled in the art to which the present disclosure belongs from the description below.

Various aspects are now described with reference to the drawings, wherein like reference numerals are used to refer to like elements generally. In the following examples, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more aspects. However, it will be apparent that such aspects may be practiced without these specific details.

FIG. 1 is a diagram illustrating a computing device for performing standardization of unstructured data using artificial intelligence according to some embodiments of the present disclosure.

FIG. 2 is a diagram illustrating an exemplary structure of an artificial intelligence-based model according to some embodiments of the present disclosure.

FIG. 3 is a diagram illustrating a method for formalizing unstructured data using artificial intelligence, performed on a computing device according to some embodiments of the present disclosure.

FIG. 4 is a diagram schematically illustrating a process of formalizing unstructured data using artificial intelligence, performed in a computing device according to some embodiments of the present disclosure.

FIG. 5 illustrates a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are set forth to provide an understanding of the present disclosure. However, it will be apparent that these embodiments may be practiced without these specific descriptions.

The terms "component," "module," "system," and the like, as used herein, refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an execution of software. For example, a component may be, but is not limited to, a procedure running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, an application running on a computing device and the computing device may both be components. One or more components may reside within a processor and/or a thread of execution. A component may be localized within a single computer. A component may be distributed between two or more computers. Furthermore, such components may execute from various computer-readable media having various data structures stored therein. The components may communicate via local and/or remote processes, for example, by a signal comprising one or more data packets (e.g., data from one component interacting with another component in a local system, a distributed system, and/or data transmitted via a network such as the Internet to another system via the signal).

Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X employs A or B" is intended to mean either of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, "X employs A or B" can apply to any of these cases. Furthermore, the terms "or" and "and/or" as used herein should be understood to refer to and include all possible combinations of one or more of the associated items listed.

Also, the terms "comprises" and/or "comprising" should be understood to mean the presence of the features and/or components. However, it should be understood that the terms "comprises" and/or "comprising" do not exclude the presence or addition of one or more other features, components, and/or groups thereof. Also, unless otherwise specified or clear from the context to refer to the singular form, the singular form as used in the specification and claims should generally be construed to mean "one or more."

And, the term "at least one of A or B" should be interpreted to mean "including only A", "including only B", or "combined in the composition of A and B".

Those skilled in the art should additionally recognize that the various illustrative logical blocks, configurations, modules, circuits, means, logics, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as combinations of electronic hardware, computer software, or both. To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application. However, such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The description of the disclosed embodiments is provided to enable a person skilled in the art to make or use the present invention. Various modifications to these embodiments will be apparent to a person skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments disclosed herein. The present invention is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

In the present disclosure, terms expressed as first, second, or third, N, are used to distinguish at least one entity. For example, entities expressed as first and second may be the same or different from each other.

FIG. 1 is a diagram illustrating a computing device for performing standardization of unstructured data using artificial intelligence according to some embodiments of the present disclosure.

The configuration of the computing device (100) illustrated in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device (100) may include other configurations for performing a computing environment of the computing device (100), and only some of the disclosed configurations may constitute the computing device (100).

A computing device (100) according to some embodiments of the present disclosure may be a device for performing formalization of unstructured data. For example, the computing device (100) may be a device that performs a process of formalizing unstructured data and storing the formalized data by utilizing artificial intelligence. The computing device (100) may include any form of server or user terminal.

A computing device (100) may include a processor (110), a memory (130), and a network unit (150).

The processor (110) may be composed of one or more cores and may include a processor for performing operations related to processing data, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), or a tensor processing unit (TPU) of the computing device (100).

According to one embodiment of the present disclosure, the processor (110) may perform operations for learning a neural network. For example, the processor (110) may perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating weights of a neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) may process learning of a network function. For example, the CPU and the GPGPU may together process learning of a network function and classification of data using a network function. In addition, in one embodiment of the present disclosure, processors of a plurality of computing devices may be used together to process learning of a network function and classification of data using a network function.

The processor (110) can typically control the overall operation of the computing device (100). The processor (110) can process signals, data, information, etc. input or output through components included in the computing device (100) or run an application program stored in the memory (130), thereby providing or processing appropriate information or functions to the user.

In one embodiment of the present disclosure, the memory (130) may store any form of information generated or determined by the processor (110) and/or any form of information received by the network unit (150). In one embodiment, the memory (130) may store a database. The database may be a collection of data stored in a form that can be processed by the computing device (100).

In one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (for example, an SD or XD memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read-Only Memory (ROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Programmable Read-Only Memory (PROM), a magnetic memory, a magnetic disk, and/or an optical disk. The computing device (100) may also operate in relation to web storage that performs the storage function of the memory (130) on the internet. The description of the memory described above is only an example, and the present disclosure is not limited thereto. The memory (130) may be operated by the processor (110).

The network unit (150) according to one embodiment of the present disclosure may include any wired or wireless communication network capable of transmitting and receiving any type of data and signals, etc., in the network expressed in the present disclosure. The techniques described in this specification may be used not only in the networks mentioned above, but also in other networks.

FIG. 2 is a diagram illustrating an exemplary structure of an artificial intelligence-based model according to some embodiments of the present disclosure.

Throughout this specification, the terms artificial intelligence-based model (e.g., summary information generation model, information classification model, etc.), computational model, neural network, network function, and neural network may be used with the same meaning (interchangeably).

A neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node. The nodes (or neurons) that make up the neural network may be interconnected by one or more links.

In a neural network, one or more nodes connected through a link can form a relationship of input node and output node relatively. The concept of input node and output node is relative, and any node in an output node relationship to one node can be in an input node relationship in a relationship to another node, and vice versa. As described above, the input node-to-output node relationship can be created based on a link. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between input nodes and output nodes connected through a single link, the data of the output node can have its value determined based on the data input to the input node. Here, the link interconnecting the input nodes and the output nodes can have a weight. The weight can be variable and can be varied by a user or an algorithm so that the neural network can perform a desired function. For example, when one or more input nodes are interconnected to one output node through each link, the output node can determine the output node value based on the values input to the input nodes connected to the output node and the weight set for the link corresponding to each input node.

As described above, a neural network is a network in which one or more nodes are interconnected through one or more links to form input node and output node relationships within the neural network. Depending on the number of nodes and links within the neural network, the relationship between the nodes and links, and the weight values assigned to each link, the characteristics of the neural network can be determined. For example, if there are two neural networks with the same number of nodes and links and different weight values for the links, the two neural networks can be recognized as being different from each other.

A neural network can be composed of a set of one or more nodes. A subset of the nodes constituting the neural network can form a layer. Some of the nodes constituting the neural network can form a layer based on distances from the initial input node. For example, a set of nodes that are n distances from the initial input node can form an n layer. The distance from the initial input node can be defined by the minimum number of links that must be passed through to reach the node from the initial input node. However, this definition of a layer is arbitrary for the purpose of explanation, and the order of a layer in a neural network can be defined in a different way than described above. For example, a layer of nodes can be defined by the distance from the final output node.

In one embodiment of the present disclosure, a set of neurons or nodes may be defined as a layer.

The initial input node may refer to one or more nodes to which data is directly input without going through a link in a relationship with other nodes in the neural network. Or, in a neural network, in a relationship between nodes based on a link, it may refer to nodes that do not have other input nodes connected by a link. Similarly, the final output node may refer to one or more nodes that do not have an output node in a relationship with other nodes in the neural network. In addition, a hidden node may refer to nodes that constitute the neural network other than the initial input node and the final output node.

According to one embodiment of the present disclosure, a neural network may be a neural network in which the number of nodes in an input layer may be the same as the number of nodes in an output layer, and the number of nodes decreases and then increases as it progresses from the input layer to a hidden layer. In addition, according to another embodiment of the present disclosure, a neural network may be a neural network in which the number of nodes in an input layer may be less than the number of nodes in an output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. In addition, according to another embodiment of the present disclosure, a neural network in which the number of nodes in an input layer may be greater than the number of nodes in an output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. In accordance with another embodiment of the present disclosure, a neural network may be a neural network in a combined form of the neural networks described above.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network, latent structures of data can be identified. A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), an auto encoder, a generative adversarial network (GAN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like. The description of the above-described deep neural network is only an example, and the present disclosure is not limited thereto.

For example, the AI-based models of the present disclosure may include transformers, generative pre-trained transformers (GPTs), BERT (Bidirectional Encoder Representations from Transformers), and the like.

The artificial intelligence-based model of the present disclosure can be represented by a network structure of any structure described above, including an input layer, a hidden layer, and an output layer.

The neural network that can be used in the artificial intelligence-based model of the present disclosure can be trained by at least one of supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, federated learning for distributed deep learning, and incremental learning. Training of the neural network can be a process of applying knowledge to the neural network to perform a specific operation.

A neural network can be trained in the direction of minimizing the error of the output. In the training of a neural network, training data is repeatedly input into the neural network, the output of the neural network for the training data and the error of the target are calculated, and the error of the neural network is backpropagated from the output layer of the neural network to the input layer in the direction of reducing the error, thereby updating the weights of each node of the neural network. In the case of supervised learning, training data in which the correct answer is labeled for each training data is used (i.e., labeled training data), and in the case of unsupervised learning, the correct answer may not be labeled for each training data. That is, for example, in the case of supervised learning for data classification, the training data may be data in which each training data is labeled with a category. Labeled training data is input into the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data.

As another example, in the case of unsupervised learning for data classification, the input learning data can be compared with the output of the neural network to calculate the error. The calculated error is backpropagated in the backward direction (i.e., from the output layer to the input layer) in the neural network, and the connection weights of each node in each layer of the neural network can be updated according to the backpropagation. The amount of change in the connection weights of each node to be updated can be determined according to the learning rate. The calculation of the neural network for the input data and the backpropagation of the error can constitute a learning cycle (epoch). The learning rate can be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, a high learning rate can be used in the early stage of learning of the neural network to allow the neural network to quickly acquire a certain level of performance, thereby increasing efficiency, and a low learning rate can be used in the later stage of learning to increase accuracy.

In learning neural networks, learning data can generally be a subset of real data (i.e., data to be processed using the learned neural network), and therefore, there can be a learning cycle in which errors for learning data decrease but errors for real data increase. Overfitting is a phenomenon in which excessive learning on learning data increases errors for real data. For example, a neural network that learned cats by showing yellow cats cannot recognize cats when it sees cats other than yellow, which can be a type of overfitting. Overfitting can act as a cause of increasing errors in machine learning algorithms. Various optimization methods can be used to prevent overfitting. To prevent overfitting, methods such as increasing learning data, regularization, dropout that deactivates some nodes of the network during the learning process, and utilizing batch normalization layers can be applied.

A computer-readable medium storing a data structure according to one embodiment of the present disclosure is disclosed. The above-described data structure can be stored in a storage unit in the present disclosure, executed by a processor, and transmitted and received by a communication unit.

A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure can refer to the organization of data to solve a specific problem (e.g., data retrieval in the shortest time, data storage, data modification). A data structure can also be defined as a physical or logical relationship between data elements designed to support a specific data processing function. A logical relationship between data elements can include a connection relationship between user-defined data elements. A physical relationship between data elements can include an actual relationship between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure can specifically include a collection of data, a relationship between data, and a function or command that can be applied to the data. An effectively designed data structure enables a computing device to perform operations while using minimal resources of the computing device. Specifically, a computing device can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and searching through an effectively designed data structure.

Data structures can be divided into linear data structures and nonlinear data structures depending on the form of the data structure. A linear data structure can be a structure in which only one piece of data is connected after another piece of data. Linear data structures can include lists, stacks, queues, and deques. A list can mean a series of data sets that have an internal order. A list can include a linked list. A linked list can be a data structure in which data is connected in a way that each piece of data has a pointer and is connected in a single line. In a linked list, a pointer can include information on the connection to the next or previous piece of data. A linked list can be expressed as a singly linked list, a doubly linked list, or a circular linked list depending on its form. A stack can be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (e.g., inserted or deleted) only at one end of the data structure. Data stored in a stack can be a data structure in which the later it enters, the sooner it comes out (LIFO - Last in First Out). A queue is a data list structure that allows limited access to data, and unlike a stack, it can be a data structure that comes out later (FIFO - First in First Out) as data is stored later. A deck can be a data structure that can process data at both ends of the data structure.

A nonlinear data structure can be a structure in which multiple data are connected behind one data. A nonlinear data structure can include a graph data structure. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices, and a graph data structure can include a tree data structure. A tree data structure can be a data structure in which there is only one path connecting two different vertices among multiple vertices included in the tree. In other words, it can be a data structure that does not form a loop in a graph data structure.

The data structure may include a neural network. And the data structure including the neural network may be stored in a computer-readable medium. The data structure including the neural network may also include preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. The data structure including the neural network may include any of the components among the above-described configurations. That is, the data structure including the neural network may be configured to include all or any combination of the preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. In addition to the above-described configurations, the data structure including the neural network may include any other information that determines the characteristics of the neural network. In addition, the data structure may include all forms of data used or generated in the computational process of the neural network, and is not limited to the foregoing. The computer-readable medium may include a computer-readable recording medium and/or a computer-readable transmission medium. The neural network may be composed of a set of interconnected computational units, which may generally be referred to as nodes. These nodes may also be referred to as neurons. The neural network is composed of at least one node.

The data structure may include data input to the neural network. The data structure including the data input to the neural network may be stored in a computer-readable medium. The data input to the neural network may include training data input during the neural network training process and/or input data input to the neural network after training is completed. The data input to the neural network may include data that has undergone preprocessing and/or data that is the target of preprocessing. The preprocessing may include a data processing process for inputting data to the neural network. Accordingly, the data structure may include data that is the target of preprocessing and data generated by the preprocessing. The above-described data structure is merely an example, and the present disclosure is not limited thereto.

The data structure may include weights of the neural network (in this specification, weights and parameters may be used with the same meaning). And the data structure including the weights of the neural network may be stored in a computer-readable medium. The neural network may include a plurality of weights. The weights may be variable and may be variable by a user or an algorithm so that the neural network may perform a desired function. For example, when one or more input nodes are interconnected to one output node by respective links, the output node may determine a data value output from the output node based on values input to the input nodes connected to the output node and weights set for links corresponding to each of the input nodes. The above-described data structure is only an example, and the present disclosure is not limited thereto.

By way of example and not limitation, the weights may include weights that are variable during the neural network learning process and/or weights that have completed neural network learning. The weights that are variable during the neural network learning process may include weights at the start of the learning cycle and/or weights that are variable during the learning cycle. The weights that have completed neural network learning may include weights that have completed the learning cycle. Accordingly, the data structure including the weights of the neural network may include the data structure including the weights that are variable during the neural network learning process and/or weights that have completed neural network learning. Therefore, the above-described weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structures are merely examples and the present disclosure is not limited thereto.

The data structure including the weights of the neural network can be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be a process of converting the data structure into a form that can be stored in the same or different computing devices and reconstructed and used later. The computing device can serialize the data structure to transmit and receive data over a network. The data structure including the weights of the serialized neural network can be reconstructed in the same computing device or another computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network can include a data structure (e.g., B-Tree, R-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in nonlinear data structures) for increasing the efficiency of computation while minimizing the use of computing device resources. The above are only examples, and the present disclosure is not limited thereto.

The data structure may include hyperparameters of the neural network. And the data structure including the hyperparameters of the neural network may be stored in a computer-readable medium. The hyperparameters may be variables that are changed by the user. The hyperparameters may include, for example, a learning rate, a cost function, a number of repetitions of a learning cycle, weight initialization (e.g., setting a range of weight values to be weight initialization targets), and the number of Hidden Units (e.g., the number of hidden layers, the number of nodes in the hidden layer). The above-described data structure is only an example, and the present disclosure is not limited thereto.

A transformer may be considered as a network function for an AI-based model (e.g., a summary information generation model, an information classification model, etc.) according to one embodiment of the present disclosure. For example, the AI-based model may be operated based on a transformer. Such an AI-based model may be operated using, for example, a recurrent neural network to which an attention algorithm is applied or a transformer to which an attention algorithm is applied.

In one embodiment, the transformer may be composed of an encoder that encodes embedded data and a decoder that decodes the encoded data. The transformer may have a structure that receives a series of data, and outputs a series of data of different types through encoding and decoding steps. In one embodiment, the series of data may be processed into a form operable by the transformer. The process of processing the series of data into a form operable by the transformer may include an embedding process. Expressions such as data token, embedding vector, embedding token, etc. may refer to data embedded in a form that can be processed by the transformer.

In order for a transformer to encode and decode a series of data, the encoders and decoders within the transformer can be processed using an attention algorithm. An attention algorithm can mean an algorithm that calculates the similarity for one or more keys for a given query, reflects the similarity given in this way to the values corresponding to each key, and then calculates an attention value by weighting the values to which the similarity is reflected.

Depending on how the query, key, and value are set, various types of attention algorithms can be classified. For example, if attention is obtained by setting the query, key, and value all to the same, this may mean a self-attention algorithm. If attention is obtained by reducing the dimension of the embedding vector and obtaining individual attention heads for each divided embedding vector to process a series of input data in parallel, this may mean a multi-head attention algorithm.

In one embodiment, the transformer may be composed of modules that perform a plurality of multi-head self-attention algorithms or multi-head encoder-decoder algorithms. In one embodiment, the transformer may also include additional components other than attention algorithms, such as an embedding layer, a normalization layer, a softmax layer, etc. A method for constructing a transformer using an attention algorithm may include a method disclosed in Vaswani et al., Attention Is All You Need, 2017 NIPS, which is incorporated herein by reference.

The transformer can be applied to various data domains such as embedded natural language, embedded sequence information, segmented image data, and audio waveforms, and can transform a series of input data into a series of output data. In order to transform data having various data domains into a series of data that can be input to the transformer, the transformer can embed the data. The transformer can process additional data expressing the relative positional relationship or phase relationship between the series of input data. Alternatively, vectors expressing the relative positional relationship or phase relationship between the input data can be additionally reflected in the series of input data, and the series of input data can be embedded. In one example, the relative positional relationship between the series of input data can include, but is not limited to, word order in a natural language sentence, the relative positional relationship of each segmented image, the time order of the segmented audio waveform, and the like. The process of adding information expressing the relative positional relationship or phase relationship between the series of input data can be referred to as positional encoding.

An example of how to embed data into a transformer is disclosed in Dosovitskiy, et al., AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE, which is incorporated herein by reference.

FIG. 3 is a diagram illustrating a method of managing a hospitalized patient performed on a computing device according to some embodiments of the present disclosure.

Embodiments of the present disclosure may include embodiments for training an artificial intelligence-based model (e.g., a summary information generation model, an information classification model, etc.) and embodiments for actually obtaining an inference result (e.g., summary information of data, a dataset, etc.) through the trained artificial intelligence-based model.

In the present disclosure, the operation of the AI-based model may be described as one of the processes of learning an AI-based model or performing inference using the AI-based model (e.g., generating summary information of data, a dataset, etc.). This has been written for convenience of explanation, and even if it is described as one of the processes of performing learning or performing inference, it should be interpreted as encompassing the other process of either learning or inference.

In one embodiment, the steps illustrated in FIG. 3 may be performed by the computing device (100). In a further embodiment, the steps in FIG. 3 may be implemented by multiple entities, such as some of the steps illustrated in FIG. 3 being performed at a user terminal and others being performed at a server.

In one embodiment, the processor (110) of the computing device (100) may obtain first text data including unstructured data. For example, the processor (110) may obtain first text data including unstructured data extracted from a medical record database (S310). For another example, the processor (110) may obtain first text data including unstructured data input by a user from a user terminal (or server) different from the computing device (100).

In one embodiment, the medical records database may be a collection of data related to the medical care of a particular person stored in a form that can be processed by a computing device (100). The processor (110) may obtain unstructured data related to medical care from the medical records database.

In one embodiment, unstructured data may be data that is not structured and has no defined structure. For example, unstructured data may include video files, audio files, photo files, document files, mail files, etc. In one embodiment, unstructured data may include unstructured medical data.

In one embodiment, the first text data may be unstructured data (e.g., medical data, etc.) expressed in text form. In one embodiment, the first text data may include unstructured data extracted from an online and/or offline unpublished medical record database. The text may include words, sentences, and/or paragraphs. The medical data may include information related to medical care of a specific person. For example, the medical data may include variables related to at least one disease in the medical field. For example, the medical data may include data including physical information, health information, and treatment information of a specific person, and may include CT image data, MRI test result data, electrocardiogram measurement result data, and electronic medical record (EMR) data of a specific person. The variables may be related to diseases, such as lifestyle habits (drinking, smoking), family history, age, gender, cholesterol level, and genetic variables.

The processor (110) can obtain summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model (S320).

The predetermined first prompt may include a request sentence (or, a question sentence) for requesting the first summary information generation model to output summary information of the first text data. For example, the first prompt may include a request sentence composed of a natural language, such as “Generate summary information of the text data that summarizes the text data.” For another example, the first prompt may include a request sentence composed of an artificial language, such as a programming language (e.g., a command sentence composed of commands, etc.).

In one embodiment, the summary information of the first text data may include text corresponding to each predetermined item in the first text data.

In one embodiment, the predetermined item may include at least one of personal information including at least one of age or gender, physical condition information related to a body, and/or disease condition information related to a disease.

In one embodiment, personal information may be information about an individual that can identify the individual alone or in combination, such as name, resident registration number, age, gender, etc.

In one embodiment, the body condition information may be information about an individual's body, such as height, weight, breathing condition, blood pressure, and the like.

In one embodiment, the disease status information may be information about an individual's disease, such as the name of the disease, the staging of the disease, whether surgery was performed, the name of the surgery, the details of the surgery, and the like.

In one embodiment, the first summary information generation model may include a Large Language Model (LLM). The Large Language Model (LLM) may refer to a language model having from billions to hundreds of billions of parameters. The Large Language Model (LLM) may achieve relatively higher performance than existing small-scale language models in various aspects of natural language processing, including translation and summarization. In one embodiment, the first summary information generation model may be tuned and used by utilizing various fine-tuning techniques, such as Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA).

In one embodiment, the first summary information generation model can be distributedly trained using a plurality of computing devices. For example, the computing device (100) pipelines the training process of the first summary information generation model, and distributes and transmits the plurality of training stages divided through the pipeline to external computing devices different from the computing device (100), thereby allowing the training process of the first summary information generation model to be processed in parallel using a plurality of computing devices. Pipelining may mean dividing a task into several stages and sequentially connecting each stage to organize the entire task.

In one embodiment, the first summary information generation model can be trained to generate summary information for input text data using second text data including unstructured data extracted from a medical record database, summary information of the second text data, and a predetermined first prompt.

In one embodiment, the first summary information generation model can be trained to receive second text data and a predetermined first prompt as input and compare the first output information with the summary information of the second text data, thereby making the first output information similar to the summary information of the second text data.

In one embodiment, the second text data may be unstructured data (e.g., medical data, etc.) expressed in text form. In one embodiment, the second text data may include unstructured data extracted from a freely available medical record database, either online and/or offline.

In one embodiment, the summary information of the second text data may include text corresponding to each predetermined item in the second text data.

In one embodiment, the summary information of the second text data can be output by the pre-trained second summary information generation model in response to inputting the second text data and the predetermined first prompt into the artificial intelligence-based pre-trained second summary information generation model.

In one embodiment, the pre-trained second summary information generation model can be pre-trained to output summary information including text corresponding to predetermined items from the third text data, using third text data including unstructured data extracted from a medical record database and a predetermined first prompt.

In one embodiment, the second summary information generation model may include a pre-trained large-scale language model. For example, the second summary information generation model may use a transformer (GPT series) model, and examples thereof include Google's Bard, Chat-GPT, XLNet, Microsoft's Turing-NLG, CLIP, etc. However, the second summary information generation model is not limited thereto, and various language models (LM: Language Models) may be used.

In one embodiment, the third text data may be unstructured data (e.g., medical data, etc.) expressed in text form. In one embodiment, the third text data may include unstructured data extracted from a medical record database that is freely available online and/or offline.

In one embodiment, the summary information of the third text data may include text corresponding to each predetermined item in the third text data.

In one embodiment, in response to inputting text data and a prompt to the second summary information generation model, the summary information of the text data output by the second summary information generation model can be used as ground truth data in the learning process of the first summary information generation model. For example, the summary information of the second text data output by the second summary information generation model can be used as ground truth data to be compared with the first output information of the first summary information generation model.

In one embodiment, the predetermined first prompt may be updated through a fine-tuning process performed in the second summary information generation model. Accordingly, the predetermined first prompt may be a final updated prompt through a fine-tuning process in the learning process of the second summary information generation model.

In one embodiment, the processor (110) may obtain a dataset in which at least one text included in the summary information of the first text data is classified by predetermined items from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or regular expression (S330).

In one embodiment, a dataset may mean a collection and/or file of related data for a specific task. A dataset may be structured in the form of a table containing columns and rows. For example, a dataset may be structured in a structured format containing columns consisting of predetermined items and rows consisting of at least one text corresponding to each column.

In one embodiment, the pre-trained information classification model may include a natural language processing model that is pre-trained to process natural language contained in text data to classify the text into predetermined categories.

In one embodiment, the natural language processing model may mean an artificial intelligence-based model that mechanically understands and processes natural language. For example, the natural language processing model may utilize BERT (Bidirectional Encoder Representations from Transformers), NER (Named Entity Recognition), etc. However, the natural language processing model is not limited thereto, and various natural language processing models may be used, such as a statistical-based natural language processing model that processes natural language by finding statistical patterns in given text data, a rule-based natural language processing model that processes text based on predefined rules, and a word embedding model that preserves semantic similarity by expressing words as vectors.

In one embodiment, a regular expression may refer to a formal language used to represent specific strings. A regular expression may represent specific patterns using predetermined metacharacters and symbols.

In one embodiment, the processor (110) can determine whether a pattern exists in the summary information of the first text data.

In one embodiment, the pattern may be a series of strings of text that represent a particular rule or structure. The pattern may include a structural pattern having a predetermined structure (e.g., format, etc.) within the text, a grammatical pattern having a predetermined grammar rule within the text, etc. Accordingly, the processor (110) may determine whether a pattern exists in the summary information of the first text data by comparing the predetermined pattern with the summary information of the first text data. In one embodiment, the summary information of the first text data may be configured with a structure corresponding to the predetermined pattern. In one embodiment, the summary information of the first text data may be configured with a non-patterned structure, not a predetermined pattern.

In one embodiment, the processor (110) can obtain the dataset by applying different methodologies for obtaining the dataset based on whether a pattern exists.

In one embodiment, if a pattern exists in the summary information of the first text data, the processor (110) may obtain a data set in which the text included in the summary information of the first text data is classified by predetermined items using a regular expression corresponding to the pattern. For example, if the summary information of the first text data corresponds to the format of a medical record, the processor (110) may obtain a data set in which the text included in the summary information of the first text data is classified by predetermined items using a regular expression corresponding to the format of the medical record.

In one embodiment, if there is no pattern in the summary information of the first text data, the processor (110) may obtain a data set in which text included in the summary information of the first text data is classified by predetermined items using a pre-learned information classification model.

In one embodiment, the processor (110) can compare at least one text classified by each predetermined item with the reference information determined for each predetermined item. The reference information is information that serves as a reference for verifying each text classified by each predetermined item, and can include information about a column determined for each predetermined item, type information of data, range information of data, length information of data, etc.

In one embodiment, the processor (110) may remove at least one error text from the data set if, as a result of comparing at least one text, there is at least one error text that does not meet criteria information determined for each predetermined item among the at least one text.

In one embodiment, the processor (110) may delete a first column corresponding to the first item in the data set if there is no text classified as the first item among the predetermined items in the data set (e.g., if the classified text is determined to be an error text and is removed, if there is no text corresponding to the first item in the text data or the summary information of the text data, etc.).

In one embodiment, the processor (110) may organize at least one error text removed from the dataset into a separate table (e.g., a temporary table, etc.) and store it in memory (130).

In one embodiment, the processor (110) may store a dataset with at least one erroneous text removed in memory (130).

For example, if the dataset from which at least one erroneous text has been removed corresponds to a predetermined structure (e.g., a common data model (CDM)), the processor (110) may store the dataset from which at least one erroneous text has been removed in the memory (130) without a separate conversion.

As another example, the processor (110) can transform and store a dataset with at least one erroneous text removed into a predetermined structure.

In one embodiment, a common data model may be a standard established for converting data of different structures into data of the same structure. For example, a common data model may be a standard for converting electronic medical record data of different structures stored in different hospitals into data of the same structure.

FIG. 4 is a diagram schematically illustrating a process of formalizing unstructured data using artificial intelligence, performed in a computing device according to some embodiments of the present disclosure.

Referring to FIG. 4, in one embodiment, the processor (110) may obtain a prompt (411) and text data (412), which are input data (410) input to artificial intelligence-based models (420, 440). For example, the processor (110) may obtain a predetermined first prompt (411) and second text data (412).

In one embodiment, the processor (110) may input the first prompt (411) and the second text data (412) into an artificial intelligence-based pre-learned second summary information generation model (420), thereby obtaining summary information (430) of the second text data from the second summary information generation model (420).

In one embodiment, the processor (110) may obtain first output information (450) from the first summary information generation model (440) by inputting the first prompt (411) and the second text data (412) into the artificial intelligence-based pre-learned first summary information generation model (440).

In one embodiment, the processor (110) may train the first summary information generation model (440) in a direction in which the summary information (430) of the second text data and the first output information (450) become similar. That is, the processor (110) may train the first summary information generation model (440) in a direction in which the error between the summary information (430) of the second text data and the first output information (450) is reduced. Accordingly, the summary information (430) of the second text data may be used as correct data (i.e., a label) in the training process of the first summary information generation model (440).

In one embodiment, the processor (110) may input input data including a prompt and text data into a first summary information generation model (440) learned in the manner described above, and obtain summary information of the text data from the first summary information generation model (440).

The processor (110) can obtain a data set (470) in which at least one text included in the summary information of the text data is classified by predetermined items from the summary information of the text data using a classification technique (460) including an artificial intelligence-based pre-learned information classification model (461) or a regular expression (462).

The processor (110) compares the criteria information determined for each predetermined item with at least one text classified for each predetermined item, and if there is at least one error text that does not match the criteria information determined for each predetermined item among the at least one text, the processor (110) can remove the at least one error text from the data set (470). The processor (110) can store the data set (480) from which the at least one error text has been removed in the memory (130).

A specific description of the process of standardizing unstructured data using artificial intelligence can be replaced with the contents described above through Figures 1 to 3, and redundant contents are omitted.

As described above with reference to FIGS. 1 to 3, the computing device (100) according to one embodiment of the present disclosure can provide faster and more accurate results to patients by reducing the burden of work required for conversion or interpretation previously performed by medical staff.

In one embodiment, the computing device (100) can increase diagnostic accuracy and data reliability by reducing human errors or inconsistencies that may occur during data entry and conversion.

In one embodiment, the computing device (100) may enable seamless information sharing among various medical institutions and medical professionals by standardizing medical records, thereby contributing to improved quality of medical care.

In one embodiment, the computing device (100) can reduce computing resources generated from unstructured data, and the technology for converting big data can be expected to have a cost-saving effect on medical research and artificial intelligence-based research.

The effects obtainable from the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs from the contents described in the present disclosure.

FIG. 5 illustrates a simplified, general schematic diagram of an exemplary computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has been described above as being generally implemented by a computing device, those skilled in the art will appreciate that the present disclosure may also be implemented in combination with computer-executable instructions and/or other program modules that may be executed on one or more computers and/or as a combination of hardware and software.

In general, program modules include routines, programs, components, data structures, and the like that perform particular tasks or implement particular abstract data types. Furthermore, those skilled in the art will appreciate that the methods of the present disclosure can be practiced with other computer system configurations, including single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, and the like, each of which may be operatively connected to one or more associated devices.

The described embodiments of the present disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Any media that can be accessed by a computer can be a computer-readable media, and such computer-readable media includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media. By way of example, and not limitation, computer-readable media can include computer-readable storage media and computer-readable transmission media. Computer-readable storage media includes both volatile and nonvolatile media, transitory and non-transitory media, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be accessed by a computer and used to store the desired information.

Computer-readable transmission media typically includes any information delivery media that embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism. The term modulated data signal means a signal that has one or more of its characteristics set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An exemplary environment for implementing various aspects of the present disclosure is illustrated, including a computer (1102) including a processing unit (1104), a system memory (1106), and a system bus (1108). The system bus (1108) couples system components, including but not limited to the system memory (1106), to the processing unit (1104). The processing unit (1104) may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be utilized as the processing unit (1104).

The system bus (1108) may be any of several types of bus structures that may additionally be interconnected to a memory bus, a peripheral bus, and a local bus using any of a variety of commercial bus architectures. The system memory (1106) includes read-only memory (ROM) (1110) and random access memory (RAM) (1112). A basic input/output system (BIOS) is stored in nonvolatile memory (1110), such as ROM, EPROM, EEPROM, and the BIOS contains basic routines that help transfer information between components within the computer (1102), such as during start-up. The RAM (1112) may also include high-speed RAM, such as static RAM, for caching data.

The computer (1102) also includes an internal hard disk drive (HDD) (1114) (e.g., EIDE, SATA)—which may also be configured for external use within a suitable chassis (not shown), a magnetic floppy disk drive (FDD) (1116) (e.g., for reading from or writing to a removable diskette (1118)), and an optical disk drive (1120) (e.g., for reading from or writing to a CD-ROM disk (1122) or other high capacity optical media such as a DVD). The hard disk drive (1114), the magnetic disk drive (1116), and the optical disk drive (1120) may be connected to the system bus (1108) by a hard disk drive interface (1124), a magnetic disk drive interface (1126), and an optical drive interface (1128), respectively. An interface (1124) for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide nonvolatile storage of data, data structures, computer-executable instructions, and the like. In the case of a computer (1102), the drives and media correspond to storing any data in a suitable digital format. While the description of computer-readable media above has referred to HDDs, removable magnetic disks, and removable optical media such as CDs or DVDs, those skilled in the art will appreciate that other types of media readable by a computer, such as zip drives, magnetic cassettes, flash memory cards, cartridges, and the like, may also be used in the exemplary operating environment, and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules, including an operating system (1130), one or more application programs (1132), other program modules (1134), and program data (1136), may be stored in the drive and RAM (1112). All or portions of the operating system, applications, modules, and/or data may also be cached in RAM (1112). It will be appreciated that the present disclosure may be implemented in a variety of commercially available operating systems or combinations of operating systems.

A user may enter commands and information into the computer (1102) via one or more wired/wireless input devices, such as a keyboard (1138) and a pointing device such as a mouse (1140). Other input devices (not shown) may include a microphone, an IR remote control, a joystick, a game pad, a stylus pen, a touch screen, and the like. These and other input devices are often connected to the processing unit (1104) via an input device interface (1142) that is coupled to the system bus (1108), but may be connected by other interfaces such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, and the like.

A monitor (1144) or other type of display device is also connected to the system bus (1108) via an interface, such as a video adapter (1146). In addition to the monitor (1144), the computer typically includes other peripheral output devices (not shown), such as speakers, a printer, and so on.

The computer (1102) may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) (1148), via wired and/or wireless communications. The remote computer(s) (1148) may be a workstation, a computing device computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other conventional network node, and may generally include many or all of the components described for the computer (1102), but for simplicity, only the memory storage device (1150) is illustrated. The logical connections illustrated include wired/wireless connections to a local area network (LAN) (1152) and/or a larger network, such as a wide area network (WAN) (1154). Such LAN and WAN networking environments are common in offices and businesses, and facilitate enterprise-wide computer networks, such as intranets, all of which may be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, the computer (1102) is connected to the local network (1152) via a wired and/or wireless communications network interface or adapter (1156). The adapter (1156) may facilitate wired or wireless communications to the LAN (1152), which may also include a wireless access point installed therein for communicating with the wireless adapter (1156). When used in a WAN networking environment, the computer (1102) may include a modem (1158), be connected to a communications computing device on the WAN (1154), or have other means for establishing communications over the WAN (1154), such as via the Internet. The modem (1158), which may be internal or external and wired or wireless, is connected to the system bus (1108) via a serial port interface (1142). In a networked environment, program modules described for the computer (1102) or portions thereof may be stored in a remote memory/storage device (1150). It will be appreciated that the network connections depicted are exemplary and other means of establishing a communications link between the computers may be used.

The computer (1102) is configured to communicate with any wireless device or object that is configured and operates in wireless communication, such as a printer, a scanner, a desktop and/or portable computer, a portable data assistant (PDA), a communication satellite, any equipment or location associated with a wireless detectable tag, and a telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, the communication may be a predefined structure as in a conventional network, or may simply be an ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows you to connect to the Internet and other things without wires. Wi-Fi is a wireless technology that allows devices, such as computers, to send and receive data, indoors and outdoors, anywhere within the coverage area of a base station, similar to a cell phone. Wi-Fi networks use a wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, to the Internet, and to wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz radio bands, at data rates of, for example, 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band).

Those skilled in the art will appreciate that information and signals may be represented using any of a variety of different technologies and techniques. For example, the data, instructions, commands, information, signals, bits, symbols, and chips referenced in the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

Those skilled in the art will appreciate that the various illustrative logical blocks, modules, processors, means, circuits, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, various forms of programs or design code (referred to herein for convenience as software), or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The various embodiments presented herein can be implemented as a method, an apparatus, or an article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, a carrier, or a medium accessible from any computer-readable storage device. For example, computer-readable storage media include, but are not limited to, magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash memory devices (e.g., EEPROMs, cards, sticks, key drives, etc.). Additionally, the various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of exemplary approaches. It is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present disclosure based on design priorities. The appended method claims provide elements of various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the embodiments disclosed herein, but is to be construed in the widest scope consistent with the principles and novel features disclosed herein.

As described above, the relevant contents have been described in the best form for carrying out the invention.

It can be used in devices and systems that utilize artificial intelligence technology to format unstructured data and store formatted data in a database.

Claims (10)

A method for formalizing unstructured data performed on a computing device, A step of obtaining first text data including unstructured data extracted from a medical record database; A step of obtaining summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model; A step of obtaining a dataset in which at least one text included in the summary information of the first text data is classified by predetermined items using an artificial intelligence-based pre-learned information classification model or a regular expression, which is a formal language used to express a specific string, from the summary information of the first text data, wherein the dataset is formed in a structured format including columns composed of the predetermined items and rows composed of the at least one text corresponding to each column; A step of comparing the reference information determined for each of the above predetermined items with at least one text classified for each of the above predetermined items; A step of removing at least one erroneous text from the dataset if, as a result of comparing each of the at least one text, there is at least one erroneous text among the at least one text that does not conform to the criterion information determined for each of the predetermined items; A step of storing a dataset from which at least one error text is removed; and A step of configuring and storing at least one error text in a temporary table; Including, The steps for obtaining the above dataset are: A step of determining whether a pattern exists in the summary information of the first text data; and A step of obtaining the dataset by applying different methodologies for obtaining the dataset for cases where the pattern exists and cases where the pattern does not exist; Including, The above pre-learned information classification model is, Includes a pre-trained natural language processing model that processes natural language contained in text data and classifies the text into predetermined items. The above first summary information generation model is, It is learned to generate summary information for input text data by using second text data including unstructured data extracted from a medical record database, summary information of the second text data, and the predetermined first prompt, and The summary information of the above second text data is, In response to inputting the second text data and the predetermined first prompt into the artificial intelligence-based pre-trained second summary information generation model, output by the pre-trained second summary information generation model, method. In paragraph 1, The above predetermined first prompt is, Including a request sentence for requesting the output of summary information of the first text data to the first summary information generation model, method. In paragraph 1, The above first summary information generation model is, By comparing the first output information output by inputting the second text data and the predetermined first prompt and the summary information of the second text data, learning is performed in the direction of reducing the error between the first output information and the summary information of the second text data. method. In paragraph 1, The above pre-learned second summary information generation model is, A third text data including unstructured data extracted from a medical record database and a pre-trained apparatus for outputting summary information including text corresponding to a predetermined item from the third text data using the pre-determined first prompt. method. In paragraph 1, In response to inputting text data and a prompt to the second summary information generation model, the summary information of the text data output by the second summary information generation model is used as ground truth data in the learning process of the first summary information generation model. method. In paragraph 1, The above predetermined items are, Personal information including at least one of age or gender; Physical condition information related to the body; and Disease status information related to the disease; Including, method. In paragraph 1, The steps for obtaining the above dataset are: A step of obtaining a dataset in which text included in the summary information of the first text data is classified into predetermined items by using a regular expression corresponding to the pattern when a pattern exists in the summary information of the first text data; Including, method. In paragraph 1, The steps for obtaining the above dataset are: If there is no pattern in the summary information of the first text data, a step of obtaining the dataset in which the text included in the summary information of the first text data is classified by predetermined items using the pre-learned information classification model; Including, method. In a computing device for performing standardization of unstructured data, processor; and Contains memory, The above processor, An act of obtaining first text data comprising unstructured data extracted from a medical record database; An operation of obtaining summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model; An operation of obtaining a dataset, in which at least one text included in the summary information of the first text data is classified by predetermined items, from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or a regular expression, which is a formal language used to express a specific string; wherein the dataset is formed in a structured format including columns composed of the predetermined items and rows composed of the at least one text corresponding to each column; An action of comparing the reference information determined for each of the above predetermined items with at least one text classified for each of the above predetermined items; An operation of removing at least one error text from the dataset if, as a result of comparing each of the at least one text, there is at least one error text among the at least one text that does not conform to the criteria information determined for each of the predetermined items; An operation of saving a dataset from which at least one error text is removed; and An action of configuring and storing at least one error text in a temporary table; To perform, The action of obtaining the above dataset is: An operation for determining whether a pattern exists in the summary information of the first text data; and An operation of obtaining the dataset by applying different methodologies for obtaining the dataset in cases where the above pattern exists and in cases where the above pattern does not exist; Including, The above pre-learned information classification model is, Includes a pre-trained natural language processing model that processes natural language contained in text data and classifies the text into predetermined items. The above first summary information generation model is, It is learned to generate summary information for input text data by using second text data including unstructured data extracted from a medical record database, summary information of the second text data, and the predetermined first prompt, and The summary information of the above second text data is, In response to inputting the second text data and the predetermined first prompt into the artificial intelligence-based pre-trained second summary information generation model, output by the pre-trained second summary information generation model, Computing device. A computer program stored in a computer-readable storage medium, wherein the computer program, when executed by a computing device, causes the computing device to perform operations for formatting unstructured data, the operations comprising: An act of obtaining first text data comprising unstructured data extracted from a medical record database; An operation of obtaining summary information of the first text data from the first text data by inputting the first text data and a predetermined first prompt into an artificial intelligence-based first summary information generation model; An operation of obtaining a dataset, in which at least one text included in the summary information of the first text data is classified by predetermined items, from the summary information of the first text data using an artificial intelligence-based pre-learned information classification model or a regular expression, which is a formal language used to express a specific string; wherein the dataset is formed in a structured format including columns composed of the predetermined items and rows composed of the at least one text corresponding to each column; An action of comparing the reference information determined for each of the above predetermined items with at least one text classified for each of the above predetermined items; An operation of removing at least one error text from the dataset if, as a result of comparing each of the at least one text, there is at least one error text among the at least one text that does not conform to the criteria information determined for each of the predetermined items; An operation of saving a dataset from which at least one error text is removed; and An action of configuring and storing at least one error text in a temporary table; Including, The action of obtaining the above dataset is: An operation for determining whether a pattern exists in the summary information of the first text data; and An operation of obtaining the dataset by applying different methodologies for obtaining the dataset in cases where the above pattern exists and in cases where the above pattern does not exist; Including, The above pre-learned information classification model is, Includes a pre-trained natural language processing model that processes natural language contained in text data and classifies the text into predetermined items. The above first summary information generation model is, It is learned to generate summary information for input text data by using second text data including unstructured data extracted from a medical record database, summary information of the second text data, and the predetermined first prompt, and The summary information of the above second text data is, In response to inputting the second text data and the predetermined first prompt into the artificial intelligence-based pre-trained second summary information generation model, output by the pre-trained second summary information generation model, A computer program stored on a computer-readable storage medium.

Images